Counting 2,784 Big Data & Machine Learning Frameworks, Toolsets, and Examples...
Suggestion? Feedback? Tweet @stkim1

Last Commit
May. 26, 2018
Mar. 14, 2018

Independently Recurrent Neural Networks

Simple TensorFlow implementation of Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN by Shuai Li et al. The author's original implementation in Theano and Lasagne can be found in Sunnydreamrain/IndRNN_Theano_Lasagne.


In IndRNNs, neurons in recurrent layers are independent from each other. The basic RNN calculates the hidden state h with h = act(W * input + U * state + b). IndRNNs use an element-wise vector multiplication u * state meaning each neuron has a single recurrent weight connected to its last hidden state.

The IndRNN

  • can be used efficiently with ReLU activation functions making it easier to stack multiple recurrent layers without saturating gradients
  • allows for better interpretability, as neurons in the same layer are independent from each other
  • prevents vanishing and exploding gradients by regulating each neuron's recurrent weight


Copy into your project.

from ind_rnn_cell import IndRNNCell

# Regulate each neuron's recurrent weight as recommended in the paper
recurrent_max = pow(2, 1 / TIME_STEPS)

cell = MultiRNNCell([IndRNNCell(128, recurrent_max_abs=recurrent_max),
                     IndRNNCell(128, recurrent_max_abs=recurrent_max)])
output, state = tf.nn.dynamic_rnn(cell, input_data, dtype=tf.float32)

Experiments in the paper

Addition Problem

See examples/ for a script reproducing the "Adding Problem" from the paper. Below are the results reproduced with the code.

Sequential MNIST

See examples/ for a script reproducing the Sequential MNIST experiment. I let it run for two days and stopped it after 60,000 training steps with a

  • Training error rate of 0.7%
  • Validation error rate of 1.1%
  • Test error rate of 1.1%


  • Python 3.4+
  • TensorFlow 1.5+